9 papers · 1 filter
Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes
Hikaru Shindo, Yu Deng, Teng Cao +5
Interactive agents trained only against task return can achieve high scores while failing to represent the mechanisms that make their actions succeed. This makes brittle behavior d…
Kintsugi: Learning Policies by Repairing Executable Knowledge Bases
Teng Cao, Yu Deng, Hikaru Shindo +6
Modern embodied agents achieve impressive performance, but their task knowledge is often stored in neural weights, latent state, or prompt-bound memory, making individual policy kn…
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
Lukas Helff, Quentin Delfosse, David Steinmann +6
As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifi…
Deep Reinforcement Learning Agents are not even close to Human Intelligence
Quentin Delfosse, Jannis Blüml, Fabian Tatai +6
Deep reinforcement learning (RL) agents achieve impressive results in a wide variety of tasks, but they lack zero-shot adaptation capabilities. While most robustness evaluations fo…
BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
Hikaru Shindo, Quentin Delfosse, Devendra Singh Dhami +1
Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural network…
Deep Reinforcement Learning via Object-Centric Attention
Jannis Blüml, Cedric Derstroff, Bjarne Gregori +3
Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant backgr…